Bridge Pier Surface Defect Detection Based on Improved YOLOV9

Cai, Hanzhe (2024) Bridge Pier Surface Defect Detection Based on Improved YOLOV9. Masters thesis, University of Wales Trinity Saint David.

Preview

Text Cai_H_MSc_Thesis.pdf - Accepted Version Available under License CC-BY-NC-ND Creative Commons Attribution Non-commercial No Derivatives. Download (3MB) | Preview

Abstract

This research introduces an innovative surface defect detection methodology specifically designed for bridge piers, which integrates state-of-the-art image enhancement algorithms with sophisticated target detection frameworks. This hybrid approach effectively addresses some of the inherent limitations observed in existing deep learning-based defect detection methodologies, particularly under conditions of suboptimal image quality and challenges related to the detection of minute targets. Comparative results demonstrate that this novel technique achieves a 3.9% increase in the mean Average Precision (mAP50) over the baseline model. Furthermore, this is accomplished with a reduction in model complexity, as evidenced by a 9.8% decrease in the number of parameters and a substantial reduction in computational demand, quantified as a 7.5 GFLOPS decrease. This study not only advances the field of structural health monitoring but also enhances the operational efficiency of automated defect detection systems.

Item Type:	Thesis (Masters)
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Theses and Dissertations > Masters Dissertations
Depositing User:	Victoria Hankinson
Date Deposited:	09 Jan 2025 15:46
Last Modified:	09 Jan 2025 15:46
URI:	https://repository.uwtsd.ac.uk/id/eprint/3308

Administrator Actions (login required)

Edit Item - Repository Staff Only